{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:47:10Z","timestamp":1776750430035,"version":"3.51.2"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Moreh and Van-Lang Institute of Semiconductor Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3680045","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:51:30Z","timestamp":1775159490000},"page":"57033-57047","source":"Crossref","is-referenced-by-count":0,"title":["UDP: Up-or-Down Precision Quantization for Large Language Models via Evolutionary Search"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7211-2637","authenticated-orcid":false,"given":"Anh-Tuan","family":"Mai","sequence":"first","affiliation":[{"name":"FPT Software AI Center, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3944-131X","authenticated-orcid":false,"given":"Tien-Son","family":"Pham","sequence":"additional","affiliation":[{"name":"Efficient Computing Research Group, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7527-6971","authenticated-orcid":false,"given":"Xuan Truong","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Next-Generation Semiconductor Convergence and Open Sharing System (COSS), Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9897-2769","authenticated-orcid":false,"given":"Thanh-Tuan","family":"Dao","sequence":"additional","affiliation":[{"name":"Efficient Computing Research Group, Vietnam National University, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref3","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref4","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref5","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv:2404.14219","author":"Marah","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3605110"},{"key":"ref7","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Han"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref9","first-page":"18518","article-title":"HAWQ-V2: Hessian aware trace-weighted quantization of neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Dong"},{"key":"ref10","first-page":"11875","article-title":"HAWQ-V3: Dyadic neural network quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00070"},{"key":"ref12","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref14","first-page":"41498","article-title":"Accurate lora-finetuning quantization of LLMs via information retention","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Qin"},{"key":"ref15","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Frantar"},{"key":"ref16","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref17","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume":"6","author":"Lin","year":"2024","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref18","article-title":"QServe: W4A8KV4 quantization and system co-design for efficient LLM serving","volume-title":"Proc. 8th Conf. Mach. Learn. Syst.","author":"Lin"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11043378"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS59952.2024.10595874"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3568702"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.63317\/2vi4sxip98b5"},{"key":"ref24","article-title":"Mitigating quantization errors due to activation spikes in GLU-based LLMs","author":"Yang","year":"2024","journal-title":"arXiv:2405.14428"},{"key":"ref25","first-page":"2316","article-title":"AsymKV: Enabling 1-bit quantization of KV cache with layer-wise asymmetric quantization configurations","volume-title":"Proc. 31st Int. Conf. Comput. Linguistics","author":"Tao"},{"key":"ref26","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref28","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref29","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"62","author":"Zhang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref32","volume-title":"NVIDIA A100 GPU Datasheet","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"ref34","volume-title":"NVIDIA L4 GPU Accelerator Product Brief","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref37","article-title":"Liger-kernel: Efficient triton kernels for LLM training","volume-title":"Proc. Pioning Open-Source Develop. ML Workshop (ICM)","author":"Hsu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710871"},{"key":"ref39","article-title":"QQQ: Quality quattuor-bit quantization for large language models","author":"Zhang","year":"2024","journal-title":"arXiv:2406.09904"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44874-8"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207413"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528692"},{"key":"ref43","article-title":"Towards a tailored mixed-precision sub-8-bit quantization scheme for gated recurrent units using genetic algorithms","author":"Miccini","year":"2024","journal-title":"arXiv:2402.12263"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2024.131231"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3557505"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069886"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2025.3589745"},{"key":"ref48","volume-title":"TensorRT-LLM","year":"2025"},{"key":"ref49","article-title":"Pointer sentinel mixture models","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Merity"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref53","article-title":"Think you have solved question answering? Try arc, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref54","article-title":"Cutlass","author":"Thakkar","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11471740.pdf?arnumber=11471740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:19:16Z","timestamp":1776748756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11471740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3680045","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}